Skip to main content
Glama

ssh_tool

Execute commands on SSH servers by specifying server names and commands to run remotely.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
serverNameYesSSH server name
commandYesCommand to execute

Implementation Reference

  • The default exported async function that serves as the main handler for the ssh_tool. It processes the request, validates parameters, establishes SSH connection, executes the command, and returns the result or error in the expected format.
    export default async (request: any) => {
        try {
            // 解析请求参数
            const { serverName, command } = request.params.arguments;
            
            // 验证参数
            if (!serverName || !command) {
                throw new Error("Missing required parameters: serverName, command");
            }
            
            // 获取SSH连接
            const conn = await getSSHConnection(serverName);
            
            // 执行命令
            const result = await executeCommand(conn, command);
            
            // 返回成功结果
            return {
                content: [
                    {
                        type: "text",
                        text: JSON.stringify({
                            server: serverName,
                            command: command,
                            ...result
                        }, null, 2)
                    }
                ]
            };
        } catch (error) {
            // 返回错误结果
            return {
                content: [
                    {
                        type: "text",
                        text: JSON.stringify({
                            error: error instanceof Error ? error.message : String(error)
                        }, null, 2)
                    }
                ],
                isError: true
            };
        }
    };
  • The input schema definition for the ssh_tool, specifying parameters serverName and command as required.
    export const schema = {
        name: "ssh_tool",
        description: "Connect to SSH server and execute commands",
        type: "object",
        properties: {
            serverName: {
                type: "string",
                description: "SSH server name",
            },
            command: {
                type: "string",
                description: "Command to execute",
            },
        },
        required: ["serverName", "command"]
    };
  • Dynamic registration of tools (including ssh_tool) in the loadTools function by scanning src/tools directory, importing modules, extracting schema, handler (default export), and destroy function, then storing in global tools and handlers maps.
      // 获取所有工具文件
      const toolFiles = fs.readdirSync(toolsDir).filter(file => file.endsWith('.js') || file.endsWith('.ts'));
    
      // 加载每个工具
      for (const file of toolFiles) {
        const toolPath = path.join(toolsDir, file);
        try {
          // 如果是重新加载,清除模块缓存
          if (reload) clearModuleCache(toolPath);
    
          // 导入模块,重新加载时添加时间戳防止缓存
          const importPath = 'file://' + toolPath + (reload ? `?update=${Date.now()}` : '');
          const { default: tool, schema, destroy } = await import(importPath);
          const toolName = path.parse(toolPath).name;
    
          // 注册工具
          tools.push({
            name: toolName,
            description: tool.description,
            inputSchema: schema,
            destroy: destroy
          });
    
          // 注册处理函数
          handlers[toolName] = async (request: ToolRequest) => { return await tool(request); };
        } catch (error) {
          console.error(`Failed to ${reload ? 'reload' : 'load'} tool ${file}:`, error);
        }
      }
    
      isLoaded = true;
      if (reload) console.log(`Successfully reloaded ${tools.length} tools`);
    
      return handlers;
    }
  • Helper function to retrieve or establish a new SSH connection using environment variables like SSH_{serverName}_URI.
    async function getSSHConnection(serverName: string): Promise<Client> {
        // 如果已有连接,直接返回
        if (sshConnections[serverName]) {
            return sshConnections[serverName];
        }
    
        // 从环境变量获取连接信息
        const sshUri = process.env[`SSH_${serverName}_URI`];
        if (!sshUri) {
            throw new Error(`SSH_${serverName}_URI environment variable must be set.`);
        }
    
        // 解析连接信息
        const [usernameAndpassword, HostAndport] = sshUri.split('@');
        const [username, password] = usernameAndpassword.split(':');
        const [host, port] = HostAndport.split(':');
    
        // 创建新连接
        return new Promise((resolve, reject) => {
            const conn = new Client();
            
            conn.on('ready', () => {
                sshConnections[serverName] = conn;
                resolve(conn);
            });
            
            conn.on('error', (err) => {
                delete sshConnections[serverName];
                reject(new Error(`SSH connection error: ${err.message}`));
            });
            
            conn.on('end', () => {
                delete sshConnections[serverName];
            });
            
            conn.connect({
                host: host,
                port: parseInt(port),
                username: username,
                password: password
            });
        });
    }
  • Helper function to execute a command over an established SSH connection and capture stdout, stderr, exit code, and signal.
    /**
     * 在SSH服务器上执行命令
     * @param conn SSH连接
     * @param command 要执行的命令
     * @returns 命令执行结果
     */
    async function executeCommand(conn: Client, command: string): Promise<{ stdout: string, stderr: string, code: number | null, signal: any }> {
        return new Promise((resolve, reject) => {
            conn.exec(command, (err, stream) => {
                if (err) {
                    reject(new Error(`Command execution failed: ${err.message}`));
                    return;
                }
                
                let stdout = '';
                let stderr = '';
                
                stream.on('close', (code, signal) => {
                    resolve({ stdout, stderr, code, signal });
                });
                
                stream.on('data', (data) => {
                    stdout += data.toString();
                });
                
                stream.stderr.on('data', (data) => {
                    stderr += data.toString();
                });
                
                stream.on('error', (err) => {
                    reject(new Error(`Stream error: ${err.message}`));
                });
            });
        });
    }
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/xiaoguomeiyitian/ToolBox'

If you have feedback or need assistance with the MCP directory API, please join our Discord server